{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:V4RMTCERZSEBO6VKEXI7LU7QIV","short_pith_number":"pith:V4RMTCER","schema_version":"1.0","canonical_sha256":"af22c98891cc88177aaa25d1f5d3f0457ac895d2c838926445dae523bf8a2420","source":{"kind":"arxiv","id":"2111.02513","version":1},"attestation_state":"computed","paper":{"title":"Evaluation of Tree Based Regression over Multiple Linear Regression for Non-normally Distributed Data in Battery Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boryann Liaw, Leslie Kerby, Shovan Chowdhury, Yuxiao Lin","submitted_at":"2021-11-03T20:28:24Z","abstract_excerpt":"Battery performance datasets are typically non-normal and multicollinear. Extrapolating such datasets for model predictions needs attention to such characteristics. This study explores the impact of data normality in building machine learning models. In this work, tree-based regression models and multiple linear regressions models are each built from a highly skewed non-normal dataset with multicollinearity and compared. Several techniques are necessary, such as data transformation, to achieve a good multiple linear regression model with this dataset; the most useful techniques are discussed. "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2111.02513","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-03T20:28:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c278c535c4a9f9a2184090b107058b2fd09320f71065d051bf81d7c0d0ed017f","abstract_canon_sha256":"2ff31b12e1dd6c70b05f642d6614cb3a1f433487aaafe67d34b3ddf7286c6731"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:05.118993Z","signature_b64":"H0kfqmVzbJhlLAqoZJ/YxafsY2d57kwumuG+ZWLENkkgewVXeRKSk0jE3Qx19uui1uYi+fxL5zzjNqyZ36ADCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af22c98891cc88177aaa25d1f5d3f0457ac895d2c838926445dae523bf8a2420","last_reissued_at":"2026-07-05T03:29:05.118465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:05.118465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of Tree Based Regression over Multiple Linear Regression for Non-normally Distributed Data in Battery Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boryann Liaw, Leslie Kerby, Shovan Chowdhury, Yuxiao Lin","submitted_at":"2021-11-03T20:28:24Z","abstract_excerpt":"Battery performance datasets are typically non-normal and multicollinear. Extrapolating such datasets for model predictions needs attention to such characteristics. This study explores the impact of data normality in building machine learning models. In this work, tree-based regression models and multiple linear regressions models are each built from a highly skewed non-normal dataset with multicollinearity and compared. Several techniques are necessary, such as data transformation, to achieve a good multiple linear regression model with this dataset; the most useful techniques are discussed. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02513","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.02513/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.02513","created_at":"2026-07-05T03:29:05.118567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.02513v1","created_at":"2026-07-05T03:29:05.118567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02513","created_at":"2026-07-05T03:29:05.118567+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4RMTCERZSEB","created_at":"2026-07-05T03:29:05.118567+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4RMTCERZSEBO6VK","created_at":"2026-07-05T03:29:05.118567+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4RMTCER","created_at":"2026-07-05T03:29:05.118567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V4RMTCERZSEBO6VKEXI7LU7QIV","json":"https://pith.science/pith/V4RMTCERZSEBO6VKEXI7LU7QIV.json","graph_json":"https://pith.science/api/pith-number/V4RMTCERZSEBO6VKEXI7LU7QIV/graph.json","events_json":"https://pith.science/api/pith-number/V4RMTCERZSEBO6VKEXI7LU7QIV/events.json","paper":"https://pith.science/paper/V4RMTCER"},"agent_actions":{"view_html":"https://pith.science/pith/V4RMTCERZSEBO6VKEXI7LU7QIV","download_json":"https://pith.science/pith/V4RMTCERZSEBO6VKEXI7LU7QIV.json","view_paper":"https://pith.science/paper/V4RMTCER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.02513&json=true","fetch_graph":"https://pith.science/api/pith-number/V4RMTCERZSEBO6VKEXI7LU7QIV/graph.json","fetch_events":"https://pith.science/api/pith-number/V4RMTCERZSEBO6VKEXI7LU7QIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4RMTCERZSEBO6VKEXI7LU7QIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4RMTCERZSEBO6VKEXI7LU7QIV/action/storage_attestation","attest_author":"https://pith.science/pith/V4RMTCERZSEBO6VKEXI7LU7QIV/action/author_attestation","sign_citation":"https://pith.science/pith/V4RMTCERZSEBO6VKEXI7LU7QIV/action/citation_signature","submit_replication":"https://pith.science/pith/V4RMTCERZSEBO6VKEXI7LU7QIV/action/replication_record"}},"created_at":"2026-07-05T03:29:05.118567+00:00","updated_at":"2026-07-05T03:29:05.118567+00:00"}